Merge branch 'for-next' into for-linus

* pcpu_chunk_page_occupied() doesn't exist in for-next.
* pcpu_chunk_addr_search() updated to use raw_smp_processor_id().

Conflicts:
	mm/percpu.c

49 files changed, 246 insertions, 745 deletions

diff --git a/arch/alpha/include/asm/percpu.h b/arch/alpha/include/asm/percpu.h
index b663f1f10b6..2c12378e3aa 100644
--- a/arch/alpha/include/asm/percpu.h
+++ b/arch/alpha/include/asm/percpu.h
@@ -1,102 +1,18 @@
 #ifndef __ALPHA_PERCPU_H
 #define __ALPHA_PERCPU_H
 
-#include <linux/compiler.h>
-#include <linux/threads.h>
-#include <linux/percpu-defs.h>
-
-/*
- * Determine the real variable name from the name visible in the
- * kernel sources.
- */
-#define per_cpu_var(var) per_cpu__##var
-
-#ifdef CONFIG_SMP
-
-/*
- * per_cpu_offset() is the offset that has to be added to a
- * percpu variable to get to the instance for a certain processor.
- */
-extern unsigned long __per_cpu_offset[NR_CPUS];
-
-#define per_cpu_offset(x) (__per_cpu_offset[x])
-
-#define __my_cpu_offset per_cpu_offset(raw_smp_processor_id())
-#ifdef CONFIG_DEBUG_PREEMPT
-#define my_cpu_offset per_cpu_offset(smp_processor_id())
-#else
-#define my_cpu_offset __my_cpu_offset
-#endif
-
-#ifndef MODULE
-#define SHIFT_PERCPU_PTR(var, offset) RELOC_HIDE(&per_cpu_var(var), (offset))
-#define PER_CPU_DEF_ATTRIBUTES
-#else
 /*
- * To calculate addresses of locally defined variables, GCC uses 32-bit
- * displacement from the GP. Which doesn't work for per cpu variables in
- * modules, as an offset to the kernel per cpu area is way above 4G.
+ * To calculate addresses of locally defined variables, GCC uses
+ * 32-bit displacement from the GP. Which doesn't work for per cpu
+ * variables in modules, as an offset to the kernel per cpu area is
+ * way above 4G.
  *
- * This forces allocation of a GOT entry for per cpu variable using
- * ldq instruction with a 'literal' relocation.
- */
-#define SHIFT_PERCPU_PTR(var, offset) ({		\
-	extern int simple_identifier_##var(void);	\
-	unsigned long __ptr, tmp_gp;			\
-	asm (  "br	%1, 1f		  	      \n\
-	1:	ldgp	%1, 0(%1)	    	      \n\
-		ldq %0, per_cpu__" #var"(%1)\t!literal"		\
-		: "=&r"(__ptr), "=&r"(tmp_gp));		\
-	(typeof(&per_cpu_var(var)))(__ptr + (offset)); })
-
-#define PER_CPU_DEF_ATTRIBUTES	__used
-
-#endif /* MODULE */
-
-/*
- * A percpu variable may point to a discarded regions. The following are
- * established ways to produce a usable pointer from the percpu variable
- * offset.
+ * Always use weak definitions for percpu variables in modules.
  */
-#define per_cpu(var, cpu) \
-	(*SHIFT_PERCPU_PTR(var, per_cpu_offset(cpu)))
-#define __get_cpu_var(var) \
-	(*SHIFT_PERCPU_PTR(var, my_cpu_offset))
-#define __raw_get_cpu_var(var) \
-	(*SHIFT_PERCPU_PTR(var, __my_cpu_offset))
-
-#else /* ! SMP */
-
-#define per_cpu(var, cpu)		(*((void)(cpu), &per_cpu_var(var)))
-#define __get_cpu_var(var)		per_cpu_var(var)
-#define __raw_get_cpu_var(var)		per_cpu_var(var)
-
-#define PER_CPU_DEF_ATTRIBUTES
-
-#endif /* SMP */
-
-#ifdef CONFIG_SMP
-#define PER_CPU_BASE_SECTION ".data.percpu"
-#else
-#define PER_CPU_BASE_SECTION ".data"
-#endif
-
-#ifdef CONFIG_SMP
-
-#ifdef MODULE
-#define PER_CPU_SHARED_ALIGNED_SECTION ""
-#else
-#define PER_CPU_SHARED_ALIGNED_SECTION ".shared_aligned"
-#endif
-#define PER_CPU_FIRST_SECTION ".first"
-
-#else
-
-#define PER_CPU_SHARED_ALIGNED_SECTION ""
-#define PER_CPU_FIRST_SECTION ""
-
+#if defined(MODULE) && defined(CONFIG_SMP)
+#define ARCH_NEEDS_WEAK_PER_CPU
 #endif
 
-#define PER_CPU_ATTRIBUTES
+#include <asm-generic/percpu.h>
 
 #endif /* __ALPHA_PERCPU_H */
diff --git a/arch/alpha/include/asm/tlbflush.h b/arch/alpha/include/asm/tlbflush.h
index 9d87aaa08c0..e89e0c2e15b 100644
--- a/arch/alpha/include/asm/tlbflush.h
+++ b/arch/alpha/include/asm/tlbflush.h
@@ -2,6 +2,7 @@
 #define _ALPHA_TLBFLUSH_H
 
 #include <linux/mm.h>
+#include <linux/sched.h>
 #include <asm/compiler.h>
 #include <asm/pgalloc.h>
 
diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S
index b9d6568e5f7..6dc03c35caa 100644
--- a/arch/alpha/kernel/vmlinux.lds.S
+++ b/arch/alpha/kernel/vmlinux.lds.S
@@ -134,13 +134,6 @@ SECTIONS
 	__bss_stop = .;
 	_end = .;
 
-	/* Sections to be discarded */
-	/DISCARD/ : {
-		EXIT_TEXT
-		EXIT_DATA
-		*(.exitcall.exit)
-	}
-
 	.mdebug 0 : {
 		*(.mdebug)
 	}
@@ -150,4 +143,6 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+
+	DISCARDS
 }
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 69371028a20..5cc4812c976 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -83,6 +83,7 @@ SECTIONS
 		EXIT_TEXT
 		EXIT_DATA
 		*(.exitcall.exit)
+		*(.discard)
 		*(.ARM.exidx.exit.text)
 		*(.ARM.extab.exit.text)
 #ifndef CONFIG_HOTPLUG_CPU
diff --git a/arch/avr32/kernel/vmlinux.lds.S b/arch/avr32/kernel/vmlinux.lds.S
index 7910d41eb88..c4b56654349 100644
--- a/arch/avr32/kernel/vmlinux.lds.S
+++ b/arch/avr32/kernel/vmlinux.lds.S
@@ -124,14 +124,11 @@ SECTIONS
 		_end = .;
 	}
 
+	DWARF_DEBUG
+
 	/* When something in the kernel is NOT compiled as a module, the module
 	 * cleanup code and data are put into these segments. Both can then be
 	 * thrown away, as cleanup code is never called unless it's a module.
 	 */
-	/DISCARD/       	: {
-		EXIT_DATA
-		*(.exitcall.exit)
-	}
-
-	DWARF_DEBUG
+	DISCARDS
 }
diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S
index 6ac307ca0d8..d7ffe299b97 100644
--- a/arch/blackfin/kernel/vmlinux.lds.S
+++ b/arch/blackfin/kernel/vmlinux.lds.S
@@ -277,8 +277,5 @@ SECTIONS
 
 	DWARF_DEBUG
 
-	/DISCARD/ :
-	{
-		*(.exitcall.exit)
-	}
+	DISCARDS
 }
diff --git a/arch/blackfin/mm/sram-alloc.c b/arch/blackfin/mm/sram-alloc.c
index 0bc3c4ef0aa..99e4dbb1dfd 100644
--- a/arch/blackfin/mm/sram-alloc.c
+++ b/arch/blackfin/mm/sram-alloc.c
@@ -42,9 +42,9 @@
 #include <asm/mem_map.h>
 #include "blackfin_sram.h"
 
-static DEFINE_PER_CPU(spinlock_t, l1sram_lock) ____cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(spinlock_t, l1_data_sram_lock) ____cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(spinlock_t, l1_inst_sram_lock) ____cacheline_aligned_in_smp;
+static DEFINE_PER_CPU_SHARED_ALIGNED(spinlock_t, l1sram_lock);
+static DEFINE_PER_CPU_SHARED_ALIGNED(spinlock_t, l1_data_sram_lock);
+static DEFINE_PER_CPU_SHARED_ALIGNED(spinlock_t, l1_inst_sram_lock);
 static spinlock_t l2_sram_lock ____cacheline_aligned_in_smp;
 
 /* the data structure for L1 scratchpad and DATA SRAM */
diff --git a/arch/cris/include/asm/mmu_context.h b/arch/cris/include/asm/mmu_context.h
index 72ba08dcfd1..1d45fd6365b 100644
--- a/arch/cris/include/asm/mmu_context.h
+++ b/arch/cris/include/asm/mmu_context.h
@@ -17,7 +17,8 @@ extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
  * registers like cr3 on the i386
  */
 
-extern volatile DEFINE_PER_CPU(pgd_t *,current_pgd); /* defined in arch/cris/mm/fault.c */
+/* defined in arch/cris/mm/fault.c */
+DECLARE_PER_CPU(pgd_t *, current_pgd);
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S
index 0d2adfc794d..6c81836b922 100644
--- a/arch/cris/kernel/vmlinux.lds.S
+++ b/arch/cris/kernel/vmlinux.lds.S
@@ -140,12 +140,7 @@ SECTIONS
 	_end = .;
 	__end = .;
 
-	/* Sections to be discarded */
-	/DISCARD/ : {
-		EXIT_TEXT
-		EXIT_DATA
-		*(.exitcall.exit)
-        }
-
 	dram_end = dram_start + (CONFIG_ETRAX_DRAM_SIZE - __CONFIG_ETRAX_VMEM_SIZE)*1024*1024;
+
+	DISCARDS
 }
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index f925115e325..4a7cdd9ea1e 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -29,7 +29,7 @@ extern void die_if_kernel(const char *, struct pt_regs *, long);
 
 /* current active page directory */
 
-volatile DEFINE_PER_CPU(pgd_t *,current_pgd);
+DEFINE_PER_CPU(pgd_t *, current_pgd);
 unsigned long cris_signal_return_page;
 
 /*
diff --git a/arch/frv/kernel/vmlinux.lds.S b/arch/frv/kernel/vmlinux.lds.S
index 22d9787406e..7dbf41f68b5 100644
--- a/arch/frv/kernel/vmlinux.lds.S
+++ b/arch/frv/kernel/vmlinux.lds.S
@@ -177,6 +177,8 @@ SECTIONS
   .debug_ranges		0 : { *(.debug_ranges) }
 
   .comment 0 : { *(.comment) }
+
+  DISCARDS
 }
 
 __kernel_image_size_no_bss = __bss_start - __kernel_image_start;
diff --git a/arch/h8300/kernel/vmlinux.lds.S b/arch/h8300/kernel/vmlinux.lds.S
index 43a87b9085b..662b02ecb86 100644
--- a/arch/h8300/kernel/vmlinux.lds.S
+++ b/arch/h8300/kernel/vmlinux.lds.S
@@ -152,9 +152,6 @@ SECTIONS
 	__end = . ;
 	__ramstart = .;
 	}
-	/DISCARD/ : {
-		*(.exitcall.exit)
-	}
         .romfs :	
 	{
 		*(.romfs*)
@@ -165,4 +162,6 @@ SECTIONS
 	COMMAND_START = . - 0x200 ;
 	__ramend = . ;
 	}
+
+	DISCARDS
 }
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 170042b420d..328d2f8b8c3 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -89,6 +89,9 @@ config GENERIC_TIME_VSYSCALL
 	bool
 	default y
 
+config HAVE_LEGACY_PER_CPU_AREA
+	def_bool y
+
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y
 
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 1b23ec126b6..1de86c96801 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -855,11 +855,17 @@ identify_cpu (struct cpuinfo_ia64 *c)
 	c->unimpl_pa_mask = ~((1L<<63) | ((1L << phys_addr_size) - 1));
 }
 
+/*
+ * In UP configuration, setup_per_cpu_areas() is defined in
+ * include/linux/percpu.h
+ */
+#ifdef CONFIG_SMP
 void __init
 setup_per_cpu_areas (void)
 {
 	/* start_kernel() requires this... */
 }
+#endif
 
 /*
  * Do the following calculations:
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index f0c521b0ba4..93ebfea43c6 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -58,7 +58,8 @@ static struct local_tlb_flush_counts {
 	unsigned int count;
 } __attribute__((__aligned__(32))) local_tlb_flush_counts[NR_CPUS];
 
-static DEFINE_PER_CPU(unsigned short, shadow_flush_counts[NR_CPUS]) ____cacheline_aligned;
+static DEFINE_PER_CPU_SHARED_ALIGNED(unsigned short [NR_CPUS],
+				     shadow_flush_counts);
 
 #define IPI_CALL_FUNC		0
 #define IPI_CPU_STOP		1
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 4a95e86b9ac..eb4214d1c5a 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -24,14 +24,14 @@ PHDRS {
 }
 SECTIONS
 {
-  /* Sections to be discarded */
+  /* unwind exit sections must be discarded before the rest of the
+     sections get included. */
   /DISCARD/ : {
-	EXIT_TEXT
-	EXIT_DATA
-	*(.exitcall.exit)
 	*(.IA_64.unwind.exit.text)
 	*(.IA_64.unwind_info.exit.text)
-	}
+	*(.comment)
+	*(.note)
+  }
 
   v = PAGE_OFFSET;	/* this symbol is here to make debugging easier... */
   phys_start = _start - LOAD_OFFSET;
@@ -316,7 +316,7 @@ SECTIONS
   .debug_funcnames 0 : { *(.debug_funcnames) }
   .debug_typenames 0 : { *(.debug_typenames) }
   .debug_varnames  0 : { *(.debug_varnames) }
-  /* These must appear regardless of  .  */
-  /DISCARD/ : { *(.comment) }
-  /DISCARD/ : { *(.note) }
+
+  /* Default discards */
+  DISCARDS
 }
diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c
index e456f062f24..ece1bf99449 100644
--- a/arch/ia64/sn/kernel/setup.c
+++ b/arch/ia64/sn/kernel/setup.c
@@ -71,7 +71,7 @@ EXPORT_SYMBOL(sn_rtc_cycles_per_second);
 DEFINE_PER_CPU(struct sn_hub_info_s, __sn_hub_info);
 EXPORT_PER_CPU_SYMBOL(__sn_hub_info);
 
-DEFINE_PER_CPU(short, __sn_cnodeid_to_nasid[MAX_COMPACT_NODES]);
+DEFINE_PER_CPU(short [MAX_COMPACT_NODES], __sn_cnodeid_to_nasid);
 EXPORT_PER_CPU_SYMBOL(__sn_cnodeid_to_nasid);
 
 DEFINE_PER_CPU(struct nodepda_s *, __sn_nodepda);
diff --git a/arch/m32r/kernel/vmlinux.lds.S b/arch/m32r/kernel/vmlinux.lds.S
index 4179adf6c62..de5e21cca6a 100644
--- a/arch/m32r/kernel/vmlinux.lds.S
+++ b/arch/m32r/kernel/vmlinux.lds.S
@@ -120,13 +120,6 @@ SECTIONS
 
   _end = . ;
 
-  /* Sections to be discarded */
-  /DISCARD/ : {
-	EXIT_TEXT
-	EXIT_DATA
-	*(.exitcall.exit)
-	}
-
   /* Stabs debugging sections.  */
   .stab 0 : { *(.stab) }
   .stabstr 0 : { *(.stabstr) }
@@ -135,4 +128,7 @@ SECTIONS
   .stab.index 0 : { *(.stab.index) }
   .stab.indexstr 0 : { *(.stab.indexstr) }
   .comment 0 : { *(.comment) }
+
+  /* Sections to be discarded */
+  DISCARDS
 }
diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds
index 01d212bb05a..47eac19e8f6 100644
--- a/arch/m68k/kernel/vmlinux-std.lds
+++ b/arch/m68k/kernel/vmlinux-std.lds
@@ -82,13 +82,6 @@ SECTIONS
 
   _end = . ;
 
-  /* Sections to be discarded */
-  /DISCARD/ : {
-	EXIT_TEXT
-	EXIT_DATA
-	*(.exitcall.exit)
-	}
-
   /* Stabs debugging sections.  */
   .stab 0 : { *(.stab) }
   .stabstr 0 : { *(.stabstr) }
@@ -97,4 +90,7 @@ SECTIONS
   .stab.index 0 : { *(.stab.index) }
   .stab.indexstr 0 : { *(.stab.indexstr) }
   .comment 0 : { *(.comment) }
+
+  /* Sections to be discarded */
+  DISCARDS
 }
diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds
index c192f773db9..03efaf04d7d 100644
--- a/arch/m68k/kernel/vmlinux-sun3.lds
+++ b/arch/m68k/kernel/vmlinux-sun3.lds
@@ -77,13 +77,6 @@ __init_begin = .;
 
   _end = . ;
 
-  /* Sections to be discarded */
-  /DISCARD/ : {
-	EXIT_TEXT
-	EXIT_DATA
-	*(.exitcall.exit)
-	}
-
   .crap : {
 	/* Stabs debugging sections.  */
 	*(.stab)
@@ -96,4 +89,6 @@ __init_begin = .;
 	*(.note)
   }
 
+  /* Sections to be discarded */
+  DISCARDS
 }
diff --git a/arch/m68knommu/kernel/vmlinux.lds.S b/arch/m68knommu/kernel/vmlinux.lds.S
index b7fe505e358..2736a5e309c 100644
--- a/arch/m68knommu/kernel/vmlinux.lds.S
+++ b/arch/m68knommu/kernel/vmlinux.lds.S
@@ -184,12 +184,6 @@ SECTIONS {
 		__init_end = .;
 	} > INIT
 
-	/DISCARD/ : {
-		EXIT_TEXT
-		EXIT_DATA
-		*(.exitcall.exit)
-	}
-
 	.bss : {
 		. = ALIGN(4);
 		_sbss = . ;
@@ -200,5 +194,6 @@ SECTIONS {
 	 	_end = . ;
 	} > BSS
 
+	DISCARDS
 }
 
diff --git a/arch/microblaze/kernel/vmlinux.lds.S b/arch/microblaze/kernel/vmlinux.lds.S
index d34d38dcd12..ec5fa91a48d 100644
--- a/arch/microblaze/kernel/vmlinux.lds.S
+++ b/arch/microblaze/kernel/vmlinux.lds.S
@@ -23,8 +23,8 @@ SECTIONS {
 		_stext = . ;
 		*(.text .text.*)
 		*(.fixup)
-
-		*(.exitcall.exit)
+               EXIT_TEXT
+               EXIT_CALL
 		SCHED_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
@@ -162,4 +162,6 @@ SECTIONS {
 	}
 	. = ALIGN(4096);
 	_end = .;
+
+	DISCARDS
 }
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 58738c8d754..1474c18fb77 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -176,17 +176,6 @@ SECTIONS
 
 	_end = . ;
 
-	/* Sections to be discarded */
-	/DISCARD/ : {
-		*(.exitcall.exit)
-
-		/* ABI crap starts here */
-		*(.MIPS.options)
-		*(.options)
-		*(.pdr)
-		*(.reginfo)
-	}
-
 	/* These mark the ABI of the kernel for debuggers.  */
 	.mdebug.abi32 : {
 		KEEP(*(.mdebug.abi32))
@@ -212,4 +201,14 @@ SECTIONS
 		*(.gptab.bss)
 		*(.gptab.sbss)
 	}
+
+	/* Sections to be discarded */
+	DISCARDS
+	/DISCARD/ : {
+		/* ABI crap starts here */
+		*(.MIPS.options)
+		*(.options)
+		*(.pdr)
+		*(.reginfo)
+	}
 }
diff --git a/arch/mn10300/kernel/vmlinux.lds.S b/arch/mn10300/kernel/vmlinux.lds.S
index f4aa0793465..76f41bdb79c 100644
--- a/arch/mn10300/kernel/vmlinux.lds.S
+++ b/arch/mn10300/kernel/vmlinux.lds.S
@@ -115,12 +115,10 @@ SECTIONS
   . = ALIGN(PAGE_SIZE);
   pg0 = .;
 
-  /* Sections to be discarded */
-  /DISCARD/ : {
-	EXIT_CALL
-	}
-
   STABS_DEBUG
 
   DWARF_DEBUG
+
+  /* Sections to be discarded */
+  DISCARDS
 }
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index fd2cc4fd2b6..aea1784edbd 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -237,9 +237,12 @@ SECTIONS
 	/* freed after init ends here */
 	_end = . ;
 
+	STABS_DEBUG
+	.note 0 : { *(.note) }
+
 	/* Sections to be discarded */
+	DISCARDS
 	/DISCARD/ : {
-		*(.exitcall.exit)
 #ifdef CONFIG_64BIT
 		/* temporary hack until binutils is fixed to not emit these
 	 	 * for static binaries
@@ -252,7 +255,4 @@ SECTIONS
 		*(.gnu.hash)
 #endif
 	}
-
-	STABS_DEBUG
-	.note 0 : { *(.note) }	
 }
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d00131ca083..2c42e1526d0 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -49,6 +49,9 @@ config GENERIC_HARDIRQS_NO__DO_IRQ
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool PPC64
 
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
+	def_bool PPC64
+
 config IRQ_PER_CPU
 	bool
 	default y
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 1f6816003eb..aa6e4500635 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -57,6 +57,7 @@
 #include <asm/cache.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
+#include <asm/mmu-hash64.h>
 #include <asm/firmware.h>
 #include <asm/xmon.h>
 #include <asm/udbg.h>
@@ -569,25 +570,53 @@ void cpu_die(void)
 }
 
 #ifdef CONFIG_SMP
-void __init setup_per_cpu_areas(void)
+#define PCPU_DYN_SIZE		()
+
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-	int i;
-	unsigned long size;
-	char *ptr;
-
-	/* Copy section for each CPU (we discard the original) */
-	size = ALIGN(__per_cpu_end - __per_cpu_start, PAGE_SIZE);
-#ifdef CONFIG_MODULES
-	if (size < PERCPU_ENOUGH_ROOM)
-		size = PERCPU_ENOUGH_ROOM;
-#endif
+	return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
+				    __pa(MAX_DMA_ADDRESS));
+}
 
-	for_each_possible_cpu(i) {
-		ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size);
+static void __init pcpu_fc_free(void *ptr, size_t size)
+{
+	free_bootmem(__pa(ptr), size);
+}
 
-		paca[i].data_offset = ptr - __per_cpu_start;
-		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
-	}
+static int pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+	if (cpu_to_node(from) == cpu_to_node(to))
+		return LOCAL_DISTANCE;
+	else
+		return REMOTE_DISTANCE;
+}
+
+void __init setup_per_cpu_areas(void)
+{
+	const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
+	size_t atom_size;
+	unsigned long delta;
+	unsigned int cpu;
+	int rc;
+
+	/*
+	 * Linear mapping is one of 4K, 1M and 16M.  For 4K, no need
+	 * to group units.  For larger mappings, use 1M atom which
+	 * should be large enough to contain a number of units.
+	 */
+	if (mmu_linear_psize == MMU_PAGE_4K)
+		atom_size = PAGE_SIZE;
+	else
+		atom_size = 1 << 20;
+
+	rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu